Superpixel level object recognition under local learning framework

Feng, Xuejiao; Lu, Huchuan; Zhang, Lihe

doi:10.1109/icip.2012.6467323

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In pruning the false candidates located on the background, global human probability, and human saliency probability are also exploited. c) Global human probability: We use the approach proposed in [29] to achieve the global human probability. The approach is based on superpixels.…”

Section: ) Appearance Potential Probabilitymentioning

confidence: 99%

Pose Estimation Based on Pose Cluster and Candidates Recombination

Xiao

Sun

2015

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Pose estimation is a task with wide application prospects in computer vision, which remains a challenging problem. In this paper, a novel pose estimation algorithm is proposed on the basis of pose clustering and body-part candidates recombination. Different from most previous methods with a single pictorial structure (PS) model, we generate mixture PS models based on clusters of the poses to achieve more faithful appearances and spatial relations estimation within each cluster. In addition, to address the problems of individual body-part false detection and double-counting, we extract some of the best estimation results in the optimal clustered model as the candidates of body parts and recombine them by solving a constrained maximization problem. Experiments on a public challenging data set show that our method is more accurate than the state-of-the-art algorithms and performs effectively in tackling the double-counting phenomena.Index Terms-Candidates recombination, mixture pictorial structure (PS) model, pose cluster, pose estimation.

show abstract

Section: ) Appearance Potential Probabilitymentioning

confidence: 99%